Transfer Learning Video Classification of Preserved, Mid-Range, and Reduced Left Ventricular Ejection Fraction in Echocardiography.

Identifying patients with left ventricular ejection fraction (EF), either reduced [EF < 40% (rEF)], mid-range [EF 40-50% (mEF)], or preserved [EF > 50% (pEF)], is considered of primary clinical importance. An end-to-end video classification using AutoML in Google Vertex AI was applied to echocardiographic recordings. Datasets balanced by majority undersampling, each corresponding to one out of three possible classifications, were obtained from the Standford EchoNet-Dynamic repository. A train-test split of 75/25 was applied. A binary video classification of rEF vs. not rEF demonstrated good performance (test dataset: ROC AUC score 0.939, accuracy 0.863, sensitivity 0.894, specificity 0.831, positive predicting value 0.842). A second binary classification of not pEF vs. pEF was slightly less performing (test dataset: ROC AUC score 0.917, accuracy 0.829, sensitivity 0.761, specificity 0.891, positive predicting value 0.888). A ternary classification was also explored, and lower performance was observed, mainly for the mEF class. A non-AutoML PyTorch implementation in open access confirmed the feasibility of our approach. With this proof of concept, end-to-end video classification based on transfer learning to categorize EF merits consideration for further evaluation in prospective clinical studies.

Hybrid Classical-Quantum Transfer Learning for Cardiomegaly Detection in Chest X-rays.

Cardiovascular diseases are among the major health problems that are likely to benefit from promising developments in quantum machine learning for medical imaging. The chest X-ray (CXR), a widely used modality, can reveal cardiomegaly, even when performed primarily for a non-cardiological indication. Based on pre-trained DenseNet-121, we designed hybrid classical-quantum (CQ) transfer learning models to detect cardiomegaly in CXRs. Using Qiskit and PennyLane, we integrated a parameterized quantum circuit into a classic network implemented in PyTorch. We mined the CheXpert public repository to create a balanced dataset with 2436 posteroanterior CXRs from different patients distributed between cardiomegaly and the control. Using k-fold cross-validation, the CQ models were trained using a state vector simulator. The normalized global effective dimension allowed us to compare the trainability in the CQ models run on Qiskit. For prediction, ROC AUC scores up to 0.93 and accuracies up to 0.87 were achieved for several CQ models, rivaling the classical-classical (CC) model used as a reference. A trustworthy Grad-CAM++ heatmap with a hot zone covering the heart was visualized more often with the QC option than that with the CC option (94% vs. 61%, p < 0.001), which may boost the rate of acceptance by health professionals.

Is there a potential benefit to increased irrigation channels during radiofrequency ablation? Results from a two-center prospective randomized study.

INTRODUCTION: Open irrigation during radiofrequency (RF) application allows a higher power delivery in the setting of temperature-controlled ablation, without causing blood clots. This study sought to evaluate the clinical value of the additional 6 supplementary channels at the proximal catheter tip compared to a standard irrigated RF catheter with 6 conventional channels present at the distal tip only. METHODS AND RESULTS: Ninety-five consecutive patients were prospectively randomized to cavotricuspid isthmus ablation using an 3.5 mm tip ablation catheter with 6 distal irrigation channels (6C; 48 patients) or an 4 mm tip ablation catheter with 12 irrigation channels (12C; 47 patients) disposed at the distal (6 channels) and proximal (6 additional channels) catheter tip. There was no significant difference between the 12C and the 6C irrigated-tip catheter concerning the total procedural duration, the RF duration, the fluoroscopic duration, and the amount of irrigation. Conversely, there were significantly more patients who experienced at least one steam pop while using the 12C as compared to the 6C irrigated-tip catheter (0% vs 13%, respectively, P = 0.018). CONCLUSION: The addition of proximal irrigation holes at the catheter tip do not facilitate lesion formation during RF ablation, but significantly increases the risk of steam pop. This is probably the consequence of an increase distortion of the temperature feedback.

Complicated forms of tachycardia-mediated cardiomyopathy associated with idiopathic left ventricular tachycardia.

Idiopathic left ventricular tachycardia is an infrequent form of ventricular tachycardia associated with a structurally normal heart. The prognosis is usually benign; however, sustained cases have been reported. In this report, we describe two cases of persistent idiopathic left ventricular tachycardia complicated by tachycardia-mediated cardiomyopathy. In the first case, the patient developed a right ventricular thrombus with subsequent pulmonary embolism. In the second case, the patient developed acute pulmonary edema. Both cases were cured by catheter ablation.

Cardiac myxoma: related to immunosuppression? A case report.

Cardiac myxomas are the most common type of primary cardiac tumours. Nevertheless, it is still a rare tumour and its relation with immunosuppressive therapy, which is essential after organ transplantation, remains uncertain. We report the case of a 30-year-old woman, who underwent kidney and pancreatic transplantation for severe nephropathy due to type I diabetes mellitus and since then, under heavy immunosuppressive treatment. Four years after surgery, a left atrial myxoma was discovered. Three other cases of cardiac myxomas following transplantation and immunodepressive status have been reported in the literature, which raises the question of an association between immunosuppression and the development of cardiac myxomas.

Fulminant hepatic necrosis resulting from heart failure.

A 60-year-old man without any history of cardiac disease was admitted for fulminant hepatic failure (FHF) with coma which revealed severe dilated cardiomyopathy. The patient improved with an adapted medical treatment and was finally discharged from the hospital. Congestive heart failure is a rare cause of FHF, but an important differential diagnosis because it has a specific and potentially efficient treatment.

Multidetector 16-slice CT scan evaluation of cavotricuspid isthmus anatomy before radiofrequency ablation.

INTRODUCTION: The anatomy of the cavotricuspid isthmus (CTI) is an important determinant of the ease of radiofrequency ablation. We evaluated the anatomy of the region with a multidetector 16-slice computed tomography (CT) scan and correlated this with subsequent procedural difficulty. METHODS: Twenty-nine patients (mean age 64 +/- 15 years) with typical atrial flutter or paroxysmal atrial fibrillation underwent ablation of the CTI. A multidetector 16-slice CT scan with contrast injection was performed in all before the procedure. RESULTS: The CTI showed marked variability as evidenced by the following measurements: length (8.2 to 32.2 mm), width (26 to 56.5 mm), depth (0 to 11 mm), thickness (0.2 to 7.5 mm), the angle between the inferior vena cava and the CTI (59.9 to 129.5 degrees ), and the length of the Eustachian valve (4.8 to 26.1 mm) present in 72% of patients. The appearance of the CTI was classified as follows into three categories: concave (72%), flat (17%), or with a sub-Eustachian recess (28%). Procedures were classified as difficult in case of failure to achieve bidirectional block or if radiofrequency duration was greater than 99% confidence interval. In the multivariate analysis, a significant correlation was present between the thickness of the CTI and procedural difficulty (p = 0.0005). CONCLUSIONS: The multidetector 16-slice CT scan with contrast injection accurately evaluates the anatomy of the CTI. The only independent anatomic parameter that predicts a more difficult procedure is the thickness of the CTI.

Treatment of Parkinson's disease with pergolide and relation to restrictive valvular heart disease.

BACKGROUND: Restrictive valvular heart disease has been reported in patients with Parkinson's disease treated with pergolide. However, few data are available on frequency, severity, dose dependency, and reversibility of pergolide-induced disease, nor on the pulmonary pressures of these patients. We aimed to clarify these characteristics in a large group of patients. METHODS: 78 patients with Parkinson's disease treated with pergolide and 18 never treated with an ergot-derived dopamine agonist (controls) were evaluated by echocardiography. A valvular scoring system was used, ranging from 1 (proven ergot-like restrictive valvular heart disease) to 4 (no disease). For the mitral valve, tenting areas and tenting distances were measured. Systolic pulmonary artery pressures were derived from the tricuspid regurgitant jet. FINDINGS: Restrictive valvular heart disease of any type was present in 26 (33%) patients in the pergolide group and none in controls (p=0.0025). Important disease (score 1 or 2) was present in 15 (19%) patients in the pergolide group and none in controls (p=0.066). Mean tenting distances and tenting areas of the mitral valve were 1.08 cm (range 0.55-2.66) and 2.39 cm2 (0.88-4.59) in the restrictive mitral valve group versus 0.63 cm (0.22-1.20) and 1.39 cm2 (0.39-3.23) in the non-restrictive group (p=0.003 and p<0.0001, respectively). Significant correlation was noted between cumulative doses of pergolide and tenting areas of the mitral valves (r=0.412, p=0.017). Mean systolic pulmonary artery pressures were 39.3 mm Hg (range 25-71) in the high-dose group versus 38.5 mm Hg (20-65) in the low-dose group (p=0.76) and 31 mm Hg (25-40) in controls (p=0.02 vs all patients given pergolide). In six patients, pergolide treatment was stopped because of restrictive valvular heart disease, in two of whom regression of disease was shown. INTERPRETATION: Restrictive valvular heart disease is not a rare finding in patients treated with pergolide. Clinicians should consider changing to a non-ergot drug if this disease is diagnosed.

Prevalence of mechanical dyssynchrony in patients with heart failure and preserved left ventricular function (a report from the Belgian Multicenter Registry on dyssynchrony).

The present study evaluated the prevalence of mechanical inter- and intraventricular dyssynchrony in patients with heart failure and preserved left ventricular (LV) ejection fraction (LVEF). We studied 138 patients with heart failure (age 67+/-11 years; 76% men); 60 patients had preserved LVEF (>40%). Using conventional Doppler echocardiography, an interventricular mechanical delay>or=40 ms was defined as interventricular dyssynchrony. Using pulse-wave tissue Doppler imaging, the time from the beginning of the QRS complex to onset of systolic motion was measured in 4 basal LV segments. A dispersion of >or=60 ms was defined as intraventricular dyssynchrony. The prevalence of inter- and intraventricular dyssynchrony was lower in patients with preserved LVEF than in those with reduced LVEF (17% vs 41%, p<0.01 for interventricular dyssynchrony, 18% vs 36%, p<0.01 for intraventricular dyssynchrony). However, patients with preserved LVEF and a QRS width>or=120 ms had higher values for the parameters for inter- and intraventricular dyssynchrony than patients with a QRS width<120 ms (interventricular mechanical delay 33+/-20 vs 20+/-16 ms, p<0.05; tissue Doppler imaging dispersion 42+/-26 vs 33+/-22 ms, p<0.05). In patients with a QRS width>or=120 ms, the prevalence of inter- and intraventricular dyssynchrony was comparable for patients with preserved and reduced LVEF (42% vs 55%, p=NS for interventricular dyssynchrony and 45% vs 46%, p=NS for intraventricular dyssynchrony). In conclusion, the prevalence of inter- and intraventricular dyssynchrony was low (17% and 18%, respectively) in patients with heart failure and preserved LVEF. However, in the presence of a QRS width of >or=120 ms, this prevalence increased to almost 50%, comparable to that for patients with heart failure and reduced LVEF and a QRS width of >or=120 ms.

Use of a new non-fluoroscopic three-dimensional mapping system in type I atrial flutter ablation.

We studied 40 patients who underwent cavo-tricuspid isthmus ablation for typical counterclockwise atrial flutter with cooled tip catheters between 2001 and 2003. Complete bi-directional isthmus block was created in all patients. A new, three-dimensional (3D), non-fluoroscopic mapping system was used in 20 patients (test group), and conventional fluoroscopy in 20 others (conventional group), using anatomic and electrophysiologic criteria in both groups. We measured the total procedure, ablation procedure, and overall fluoroscopy times, and the total number of radiofrequency (RF) applications delivered in the two groups. The overall fluoroscopy time was shorter in the test group (mean 8.8 minutes, range 2-17 minutes) than the conventional group (29.7 minutes, range 12-57 minutes; P < 0.001). Though the overall procedure time was similar in both groups (92.5 +/- 28.6 minutes vs 106.5 +/- 20.9 minutes; P = 0.067) the ablation duration (25.1 +/- 6.6 minutes versus 43.3 +/- 19.6 minutes; P = 0.0051) and the total RF applications (10.6 +/- 9.4 versus 16.4 +/- 9.4; P = 0.044) were smaller in the test group. The use of a new, 3D non-fluoroscopic mapping system markedly reduced the fluoroscopy exposure during typical atrial flutter ablation. It was also associated with a significant reduction in ablation time and in the number of RF applications. Since atrial flutter ablation is one of the most frequently performed procedures, this system may significantly reduce the overall amount of radiation exposure in high-volume laboratories.